检索结果-内蒙古大学图书馆

Lightweight Task-Oriented Semantic Communication Empowered by Large-Scale AI Models

IEEE Transactions on Vehicular Technology 2025年

作者： Liu, Chuanhong Guo, Caili Yang, Yang Chen, Mingzhe Quek, Tony Q. S. Beijing University of Posts and Telecommunications Beijing Key Laboratory of Network System Architecture and Convergence School of Information and Communication Engineering Beijing100876 China Beijing University of Posts and Telecommunications Beijing Laboratory of Advanced Information Networks School of Information and Communication Engineering Beijing100876 China University of Miami Department of Electrical and Computer Engineering Institute for Data Science and Computing Coral GablesFL United States Singapore University of Technology and Design Dept. of Information Systems Technology and Design 487372 Singapore

Recent studies have focused on leveraging large-scale artificial intelligence (LAI) models to improve semantic representation and compression capabilities. However, the substantial computational demands of LAI models pose significant challenges for real-time communication scenarios. To address this, this paper proposes utilizing knowledge distillation (KD) techniques to extract and condense knowledge from LAI models, effectively reducing model complexity and computation latency. Nevertheless, the inherent complexity of LAI models leads to prolonged inference times during distillation, while their lack of channel awareness compromises the distillation performance. These limitations make standard KD methods unsuitable for task-oriented semantic communication scenarios. To address these issues, we propose a fast distillation method featuring a pre-stored compression mechanism that eliminates the need for repetitive inference, significantly improving efficiency. Furthermore, a channel adaptive module is incorporated to dynamically adjust the transmitted semantic information based on varying channel conditions, enhancing communication reliability and adaptability. In addition, an information bottleneck-based loss function is derived to guide the fast distillation process. Simulation results verify that the proposed scheme outperform baselines in term of task accuracy, model size, computation latency, and training data requirements. © 1967-2012 IEEE.

关键词： NP-hard

来源：评论

学校读者我要写书评

暂无评论

Optimizing Brain Tumor Segmentation with Advanced Superpixel Techniques in Conjunction with Deep Learning Methods

Optimizing Brain Tumor Segmentation with Advanced Superpixel...

引用

Evolutionary Algorithms and Soft Computing Techniques (EASCT), International Conference on

作者： Kanegonda Ravi Chythanya Aruna S Jayakumar Karuppaiah S. Benjamin Arul Piyush Kumar Pareek School of Computer Science & Artificial Intelligence SR University Warangal India Dept. of Computational Intelligence SRMIST Chennai India Department of Biomedical Engineering KIT- Kalaignarkarunanidhi Institute of Technology Coimbatore India School of Engineering and Technology Jeppiaar University Chennai India Department of AI and ML Nitte Meenakshi Institute of Technology Bengaluru India

Brain tumor segmentation in medical imaging is crucial for precise diagnosis and treatment planning. To address these issues, our research leverages deep learning techniques and introduces an innovative approach that combines various key components. Our methodology includes preprocessing, superpixel segmentation, feature extraction, and the use of a Convolutional Neural Network (CNN) to achieve precise brain tumor segmentation. This approach is driven by the necessity for improved accuracy and efficiency, especially with diverse clinical data and tumor types, like the challenging BraTS 2018 dataset, consisting of 1070 T1W-CE MRI images. This approach using metrics such as the Dice score, sensitivity, and specificity, which demonstrate the superior performance of our superpixel model in brain tumor segmentation. This proposed method yields exceptional results, with a Dice score of 97.06%, sensitivity of 99.05%, and specificity of 99.83%, highlighting its accuracy and effectiveness in tumor segmentation when compared to existing methods such as UNet, Kapur entropy, and rough set theory. This research significantly advances the state of the art and offers great promise for enhancing medical image analysis in this critical field.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Reeb Graph Metrics from the Ground Up

arXiv

引用

arXiv 2021年

作者： Bollen, Brian Chambers, Erin Levine, Joshua A. Munch, Elizabeth Dept. of Mathematics University of Arizona United States Dept. of Computer Science University of Arizona United States Dept. of Computer Science St. Louis University United States Dept. of Computational Mathematics Science and Engineering Michigan State University United States

The Reeb graph has been utilized in various applications including the analysis of scalar fields. Recently, research has been focused on using topological signatures such as the Reeb graph to compare multiple scalar fields by defining distance metrics on the topological signatures themselves. Here we survey five existing metrics that have been defined on Reeb graphs: the bottleneck distance, the interleaving distance, functional distortion distance, the Reeb graph edit distance, and the universal edit distance. Our goal is to (1) provide definitions and concrete examples of these distances in order to develop the intuition of the reader, (2) visit previously proven results of stability, universality, and discriminativity, (3) identify and complete any remaining properties which have only been proven (or disproven) for a subset of these metrics, (4) expand the taxonomy of the bottleneck distance to better distinguish between variations which have been commonly miscited, and (5) reconcile the various definitions and requirements on the underlying spaces for these metrics to be defined and properties to be proven. Copyright © 2021, The Authors. All rights reserved.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

A Blockchain-Based data-Sharing Framework for Cloud Based Internet of Things Systems with Efficient Smart Contracts

A Blockchain-Based Data-Sharing Framework for Cloud Based In...

引用

IEEE International Conference on Communications Workshops, ICC

作者： Kadiyala Ramana R.Madana Mohana C. Kishor Kumar Reddy Gautam Srivastava Thippa Reddy Gadekallu Department of Artificial Intelligence & Data Science Chaitanya Bharathi Institute of Technology Hyderabad India Department of CSE Stanley College of Engineering and Technology for Women Hyderabad India Dept. of Math and Computer Science Brandon University Brandon MB Canada Vellore Institute of Technology Vellore India Department of Electrical and Computer Engineering Lebanese American University Byblos Lebanon

As the Internet of Things (IoT) has advanced, data sharing has become a crucial function of cloud computing. However, data security remains a significant challenge in this field. This research proposes a blockchain-based data-sharing system that prioritizes data security and efficiency. The system includes efficient smart contracts and security gateways that record data in the cloud using blockchain. If suspicious behaviour is detected, the blockchain is checked by the centralized cloud, and the responsible party for any malicious gateway behaviour is held accountable. Authentication and data exchange algorithms are used to ensure data security. Additionally, to reduce the burden on end-users, smart contracts in blockchain use highly complex partial decryption algorithms. To satisfy data restriction safety criteria, blockchain achieves traceability of historical actions through open and transparent supervision. Experimental findings demonstrate that the proposed technique is effective in ensuring the safety and efficiency of information exchange between various clients.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ChatGPT-guided Semantics for Zero-shot Learning

arXiv

引用

arXiv 2023年

作者： Shubho, Fahimul Hoque Chowdhury, Townim Faisal Cheraghian, Ali Saberi, Morteza Mohammed, Nabeel Rahman, Shafin Dept. of Electrical and Computer Engineering North South University Bangladesh Australian Institute for Machine Learning University of Adelaide Australia Data61 Commonwealth Scientific and Industrial Research Organisation Australia School of Computer Science and DSI University of Technology Sydney Australia

Zero-shot learning (ZSL) aims to classify objects that are not observed or seen during training. It relies on class semantic description to transfer knowledge from the seen classes to the unseen classes. Existing methods of obtaining class semantics include manual attributes or automatic word vectors from language models (like word2vec). We know attribute annotation is costly, whereas automatic word vectors are relatively noisy. To address this problem, we explore how ChatGPT, a large language model, can enhance class semantics for ZSL tasks. ChatGPT can be a helpful source to obtain text descriptions for each class containing related attributes and semantics. We use the word2vec model to get a word vector using the texts from ChatGPT. Then, we enrich word vectors by combining the word embeddings from class names and descriptions generated by ChatGPT. More specifically, we leverage ChatGPT to provide extra supervision for the class description, eventually benefiting ZSL models. We evaluate our approach on various 2D image (CUB and AwA) and 3D point cloud (ModelNet10, ModelNet40, and ScanObjectNN) datasets and show that it improves ZSL performance. Our work contributes to the ZSL literature by applying ChatGPT for class semantics enhancement and proposing a novel word vector fusion method. © 2023, CC BY.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

ChatGPT-guided Semantics for Zero-shot Learning

ChatGPT-guided Semantics for Zero-shot Learning

引用

Proceedings of the Digital Image Computing: Technqiues and Applications (DICTA)

作者： Fahimul Hoque Shubho Townim Faisal Chowdhury Ali Cheraghian Morteza Saberi Nabeel Mohammed Shafin Rahman Dept. of Electrical and Computer Engineering North South University Bangladesh Australian Institute for Machine Learning University of Adelaide Australia Data61 Commonwealth Scientific and Industrial Research Organisation Australia School of Computer Science and DSI University of Technology Sydney Australia

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Roadmap on Optics for Terawatt Scale Photovoltaics

A Roadmap on Optics for Terawatt Scale Photovoltaics

引用

2024 Solar Energy and Light-Emitting Devices, SOLED 2024

作者： Jäger, Klaus Burger, Sven Aeberhard, Urs Llado, Esther Alarcon Bläsi, Benedikt Ehrler, Bruno Favre, Wilfried Fejfar, Antonín Gageot, Tristan Gordon, Ivan Helmers, Henning Höhn, Oliver Isabella, Olindo Jošt, Marko Ledinský, Martin Mandal, Jyotirmoy Manley, Phillip Munoz, Delfina Lizcano, Juan Camilo Ortiz Paetzold, Ulrich W. Raman, Aaswath P. Sai, Hitoshi Saive, Rebecca Schmid, Martina Yablonovitch, Eli Becker, Christiane Dept. Optics for Solar Energy Helmholtz-Zentrum Berlin für Materialien und Energie GmbH Kekuléstraße 5 Berlin12489 Germany Computational Nano Optics Zuse Institute Berlin Takustraße 7 Berlin14195 Germany JCMwave GmbH Bolivarallee 22 Berlin14050 Germany Fluxim AG Katharina-Sulzer-Platz 2 Winterthur8400 Switzerland AMOLF Science Park 104 Amsterdam1098 XG Netherlands Fraunhofer Institute for Solar Energy Systems ISE Heidenhofstraße 2 Freiburg79100 Germany CEA-INES LITEN 50 Avenue du Lac Léman Le Bourget-du-Lac73375 France FZU - Institute of Physics of the Czech Academy of Sciences Na Slovance 1999/2 Prague 8182 00 Czech Republic IMEC Kapeldreef 75 Leuven3001 Belgium Photovoltaic Materials and Devices Laboratory Delft University of Technology Mekelweg 4 Delft2628 CD Netherlands Faculty of Electrical Engineering University of Ljubljana Tržaška 25 Ljubljana1000 Slovenia Dept. of Civil and Environmental Engineering Princeton University E209A Engineering Quadrangle PrincetonNJ08544 United States Institute of Microstructure Technology Karlsruhe Institute of Technology Eggenstein-Leopoldshafen76344 Germany Light Technology Institute Karlsruhe Institute of Technology Karlsruhe76131 Germany Dept. of Materials Science and Engineering University of California Los Angeles Los AngelesCA90024 United States Ibaraki Tsukuba305-8568 Japan MESA+ Institute for Nanotechnology Inorganic Materials Science University of Twente Enschede7522 Netherlands University of Duisburg-Essen Forsthausweg 2 Duisburg47057 Germany Dept. of Electrical Engineering and Computer Sciences University of California Berkeley BerkeleyCA94720 United States

The ongoing development of photovoltaics into terawatt scale poses a number of challenges where the optics and photonics communities can contribute. An international consortium recently compiled a roadmap that elabora...

关键词：

来源：评论

学校读者我要写书评

暂无评论

Intra-datacenter Load Balancing in a Federated Cloud with Throttled Algorithm

Intra-Datacenter Load Balancing in a Federated Cloud with Th...

引用

science, engineering and Business for Sustainable Development Goals (SEB-SDG), International Conference on

作者： Damola Gideon Akinola Emmanuel Adetiba Abdultaofeek Abayomi Uche Nnaji Surendra Thakur Sibusiso Moyo Department of Electrical and Information Engineering Covenant Applied Informatics and Communications African Center of Excellence Covenant University Ota Nigeria HRA Institute for Systems Science Durban University of Technology Durban South Africa Department of Information and Communication Technology Mangosuthu University of Technology Durban South Africa Dept. of Computer and Information Science Covenant Applied Informatics and Communications African Center of Excellence Covenant University Ota Nigeria KZN e-Skills CoLab Durban University of Technology Durban South Africa School for Data Science and Computational Thinking and Department of Mathematical Sciences Stellenbosch University Stellenbosch South Africa

ISBN: (数字)9798350358155

ISBN: (纸本)9798350358162

The emergence of cloud computing technology has motivated a very high number of users in different organizations to access its services in running and delivering their various operations and services. However, this surge of cloud users has led to the problem of uneven load sharing among the cloud computing infrastructures. As a result, federated cloud infrastructure was initiated to provide more cloud computing resources to accommodate more cloud users’ requests and also to provide equal requests mapping with the available cloud resources. Nevertheless, the issue of unequal allocation of requests within the datacenter(s) that makes up the federated cloud environment still persists. This research work presents an intra-datacenter load balancing algorithm in a federated cloud environment named; the intra-balancer adapted throttled algorithm to evenly distribute requests in each datacenter that formulate the federated cloud infrastructures. The simulation of the intra-balancer was carried out in CloudAnalyst, the results of the implementation showed that the intra-balancer outperformed the Round-Robin and ESCE with 98.93ms and 2.26ms for the response and processing time respectively. The results assert that the intra-balancer algorithm provides a better load balancing solution in a federated cloud environment.

关键词： Computers Cloud computing Organizations Load management Resource management Time factors Task analysis

来源：评论

学校读者我要写书评

暂无评论

Multimodal signals subject authentication system 18

Multimodal signals subject authentication system

引用

18th International Conference on Electrical engineering/Electronics, Computer, Telecommunications and Information Technology, ECTI-CON 2021

作者： Alotaiby, Turky N. Alshebeili, Saleh A. Alotaibi, Gaseb King Abdulaziz City for Science and Technology The National Center for Data Analytics and Artificial Intelligence Riyadh Saudi Arabia King Saud University Dept. of Electrical Engineering Ryiadh Saudi Arabia Ministry of Interior Public Security Riyadh Saudi Arabia

ISBN: (纸本)9780738111278

The ever increasing number of e-services provided to users necessitates the efficient and accurate verification of user identity. In this work, we present a user authentication model based on multimodal signals. More specifically, we investigate the extraction of statistical features using various segment lengths of photoplethysmogram (PPG), electrocardiogram (ECG) and capnogram (CO2) signals and generate a feature vector using different fusion approaches. In addition, adding to the feature vector additional features extracted from the 1st derivative of the corresponding signal is explored. Finally, a classifier is used for identity authentication. The proposed authentication system achieved an average authentication accuracy of 99.76% using a 1 second segment length and a random forest classifier. © 2021 IEEE.

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

Multi-modal Representation Learning Enables Accurate Protein Function Prediction in Low-data Setting

arXiv

引用

arXiv 2024年

作者： Ünsal, Serbulent Özdemir, Sinem Kasap, Bünyamin Kalaycı, M. Erşan Turhan, Kemal Doğan, Tunca Acar, Aybar C. Department of Biostatistics and Medical Informatics Faculty of Medicine Graduate School of Health Sciences Karadeniz Technical University Trabzon Turkey Graduate School of Informatics Middle East Technical University Ankara Turkey Health Sciences University Trabzon Kanuni Training and Research Hospital Medical Microbiology Laboratory Trabzon Turkey Biological Data Science Lab Dept. of Computer Engineering Department of Computer Engineering Hacettepe University Ankara Turkey Dept. of Bioinformatics Graduate School of Health Sciences Hacettepe University Ankara Turkey

In this study, we propose HOPER (HOlistic ProtEin Representation), a novel multimodal learning framework designed to enhance protein function prediction (PFP) in low-data settings. The challenge of predicting protein functions is compounded by the limited availability of labeled data. Traditional machine learning models already struggle in such cases, and while deep learning models excel with abundant data, they also face difficulties when data is scarce. HOPER addresses this issue by integrating three distinct modalities—protein sequences, biomedical text, and protein-protein interaction (PPI) networks—to create a comprehensive protein representation. The model utilizes autoencoders to generate holistic embeddings, which are then employed for PFP tasks using transfer learning. HOPER outperforms existing methods on a benchmark dataset across all Gene Ontology categories, i.e., molecular function, biological process, and cellular component. Additionally, we demonstrate its practical utility by identifying new immune-escape proteins in lung adenocarcinoma, offering insights into potential therapeutic targets. Our results highlight the effectiveness of multimodal representation learning for overcoming data limitations in biological research, potentially enabling more accurate and scalable protein function prediction. HOPER source code and datasets are available at https://***/kansil/HOPER © 2024, CC BY-NC-ND.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：